Generative AI models have shown remarkable capabilities in creating diverse content, including text, image, and voice. However, Large Language Models often struggle to maintain thematic consistency and structure when used for narrative generation, especially when creating longer and more complex stories. When generative AI aims at producing high-quality narratives, having mechanisms to guide the creative process and ensure thematic consistency is crucial. This project explores new methods to guide the generation of narratives using AI, by incorporating narrative patterns, genre structures, and semiotic relations, to improve the overall quality and coherence of the generated stories.

Quests are a fundamental storytelling mechanism used by computer role-playing games (RPGs) to engage and involve players in the game's narrative. Although RPGs have evolved in many ways in the last years, their basic narrative structure is still based on static plots manually created by game designers. This project explores the generation of dynamic and interactive quests for games using hierarchical task decomposition, planning under nondeterminism, player modeling, and genetic algorithms.

Fear is a basic human emotion that can be triggered by different situations, which vary from person to person. However, game developers usually design horror games based on a general knowledge of what most players fear, which does not guarantee a satisfying horror experience for everyone. When a horror game aims at intensifying the fear evoked in individual players, having useful information about the fears of the current player is vital to promote more frightening experiences. This project explores new methods to create adaptive horror games by using player modeling techniques to identify what individual players fear and adapt the content of the game to intensify the fear evoked in players.

An intriguing phenomenon in human storytelling - an inexhaustible source of inspiration for digital storytelling - is our ability to still recognize a story that the narrator has felt free to change to a considerable extent. However, observing how folktales have appeared and been disseminated through different countries over the centuries, we shall notice that our favorite stories have evolved no less dramatically in the course of the oral storytelling tradition. Founded on the classification of types and motifs contained in the Index of Antti Aarne and Stith Thompson, this research project attempts to understand how narrative variants emerge in order to create new narrative generation methods.